1 / 22

Wrapping Up

Wrapping Up. Ling575 Spoken Dialog Systems June 5, 2013. Roadmap. Overview Distinctive factors in dialog: Human-human Human-computer Dialog components & dialog management Specialized topics: Detailed analysis of: Distinctive factors Techniques and applications Discussion:

alida
Download Presentation

Wrapping Up

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript

  1. Wrapping Up Ling575 Spoken Dialog Systems June 5, 2013

  2. Roadmap • Overview • Distinctive factors in dialog: • Human-human • Human-computer • Dialog components & dialog management • Specialized topics: • Detailed analysis of: • Distinctive factors • Techniques and applications • Discussion: • Trends, techniques, interrelations

  3. Characteristics of Dialog • Human-human: • Multi-party interaction: • Flexible turn-taking, mixed initiative • Speech acts: • Actions via speech, levels of interpretation • Implicature: • Grice’s maxims • Cooperativity & closure: • Grounding and levels of display • Corrections, repairs, and confirmations

  4. Characteristics of Dialog • Human-computer – most deployed systems • Multi-party interaction:

  5. Characteristics of Dialog • Human-computer – most deployed systems • Multi-party interaction: • Rigid silence-based turn-taking, system or “mixed” initiative • Speech acts:

  6. Characteristics of Dialog • Human-computer – most deployed systems • Multi-party interaction: • Rigid silence-based turn-taking, system or “mixed” initiative • Speech acts: • Actions via speech: dialog acts, NLU • Implicature:

  7. Characteristics of Dialog • Human-computer – most deployed systems • Multi-party interaction: • Rigid silence-based turn-taking, system or “mixed” initiative • Speech acts: • Actions via speech: dialog acts, NLU • Implicature: • Um… depends on dialog management, NLU • Grounding:

  8. Characteristics of Dialog • Human-computer – most deployed systems • Multi-party interaction: • Rigid silence-based turn-taking, system or “mixed” initiative • Speech acts: • Actions via speech: dialog acts, NLU • Implicature: • Um… depends on dialog management, NLU • Grounding: • Confirmation: implicit/explicit: learned? • Corrections, repairs: problematic • Why?

  9. Characteristics of Dialog • Human-computer – most deployed systems • Multi-party interaction: • Rigid silence-based turn-taking, system or “mixed” initiative • Speech acts: • Actions via speech: dialog acts, NLU • Implicature: • Um… depends on dialog management, NLU • Grounding: • Confirmation: implicit/explicit: learned? • Corrections, repairs: problematic • Constrained by complexity, processing, speed, etc

  10. Dialog System Components • HMM-based ASR models • NLU: call-routing, semantic grammars • Dialog acts and recognition • Dialog management: • Finite-state • Frame-based • VoiceXML • Information state • Statistical dialog management • Lots of examples!

  11. Topics • In-depth discussions: • Computational approaches to make human-computer interaction more like human-human interaction • Many issues raised in characterizing dialog: • Multi-party

  12. Topics • In-depth discussions: • Computational approaches to make human-computer interaction more like human-human interaction • Many issues raised in characterizing dialog: • Multi-party: multi-party interaction, turn-taking, initiative • Grounding

  13. Topics • In-depth discussions: • Computational approaches to make human-computer interaction more like human-human interaction • Many issues raised in characterizing dialog: • Multi-party: multi-party interaction, turn-taking, initiative • Grounding: Miscommunication & repair, incremental processing • Interpretation:

  14. Topics • In-depth discussions: • Computational approaches to make human-computer interaction more like human-human interaction • Many issues raised in characterizing dialog: • Multi-party: multi-party interaction, turn-taking, initiative • Grounding: Miscommunication & repair, incremental processing • Interpretation: Reference, affect, subjectivity, personification, information structure, prosody • Multi-modality • Applications and issues: • Tutoring, machine translation, information-seeking • Non-native speech

  15. Interconnections Apps: MT Tutoring Non-native Affect Turn-taking Sentiment Info. Struct Reference Increment Prosody Initiative Persona Multi-party Multi-modality Miscommunication

  16. Interconnections Apps: MT Tutoring Non-native Affect Turn-taking Sentiment Info. Struct Reference Increment Prosody Initiative Persona Multi-party Multi-modality Miscommunication

  17. Techniques & Sources of Information • Range of techniques:

  18. Techniques & Sources of Information • Range of techniques: • Deep processing, shallow processing, manual rules • Machine learning:

  19. Techniques & Sources of Information • Range of techniques: • Deep processing, shallow processing, manual rules • Machine learning: • Anything from decision trees to POMDPs • Information sources:

  20. Techniques & Sources of Information • Range of techniques: • Deep processing, shallow processing, manual rules • Machine learning: • Anything from decision trees to POMDPs • Information sources: • Acoustic, lexical, prosodic, timing, syntactic, semantic, pragmatic, etc Multimodal: gaze, gesture, etc • Integration

  21. Techniques & Sources of Information • Range of techniques: • Deep processing, shallow processing, manual rules • Machine learning: • Anything from decision trees to POMDPs • Information sources: • Acoustic, lexical, prosodic, timing, syntactic, semantic, pragmatic, etc Multimodal: gaze, gesture, etc • Integration: Complex and varied • Huge feature vectors, tandem models, blackboards, learned • Substantial strides, but huge remaining challenges

  22. Questions? • Favorite topic? • Most surprising result? • Most obvious result? • Most surprising gap?

More Related